In this paper we present an adaptive method for graphic symbol representation based on shape contexts. The proposed descriptor is invariant under classical geometric transforms (r...
In this poster we present an overview of the techniques we used to develop and evaluate a text categorisation system for the PRINCIP project which sets out to automatically classi...
For meaning representations in NLP, we focus our attention on thematic aspects and conceptual vectors. The learning strategy of conceptual vectors relies on a morphosyntaxic analy...
Didier Schwab, Mathieu Lafourcade, Violaine Prince
Raised line patterns are used extensively in the design of tactile graphics for persons with visual impairments. A tactile stroke pattern was therefore developed to enable the rend...
Most recent class-level object recognition systems work with visual words, i.e., vector quantized local descriptors. In this paper we examine the feasibility of a dataindependent ...